Coding with AI / RTX 3060
RTX 3060
Memory: 12 GB.
Memory bandwidth: 360 GB/s.
Generation speed is bound by the chip's bandwidth; memory decides which models fit.
smartgpt-oss-20b60.7% on SWE-bench Verifiedfrozen27 tok/s · measured How to run
gpt-oss-20b smart
-
Score: 60.7% (SWE-bench Verified),
source
-
Speed: 27 tok/s (measured, source)
- Conditions: engine llama.cpp, quant MXFP4, context 128
- Min memory: 12 GB
- Command:
llama-server -m gpt-oss-20b-MXFP4.gguf
Every number above is either a measurement with a source or a labeled estimate with a method.
Unlabeled estimates do not exist on this site.
Ceiling timeline
The strongest model fitting RTX 3060 (12 GB) at its release date, by SWE-bench Verified.
- 2025-08-05 gpt-oss-20b 60.7%